Sound holds a wealth of information, and with AMBIsense, we offer an all-encompassing suite of multi-classification sound monitoring solutions designed for a comprehensive analysis of the environmental soundscape. Our technology specializes in detecting and recognizing sounds, localizing and tracking sound sources, and estimating various acoustic parameters to provide valuable insights and actionable data. This enhances situational awareness and improves governance.
As such AMBIsense sound sensing is an integral component of data-driven governance within the Digital Twin evolution, serving as a vital tool for understanding and managing acoustic environments.
Tailored for public authorities, industrial environments, and corporate settings, our AMBIsense solutions are built upon the latest artificial intelligence algorithms for machine listening. This approach provides comprehensive noise monitoring and soundscape analysis, supporting better environmental and (proactive) situational management.
Our solutions make use of robust, highly customizable cloud based IoT sensor nodes that are extensible with a wide range of sensors. These sensor nodes form the core hardware components of our smart sound & vibration monitoring solutions.
This hardware design, along with embedded software for data capture and sensor data management, and the application of machine learning algorithms for data analysis and computational modeling, as well as the development of web-based front-ends for data visualization and presentation, define the complete AMBIsense solution.
Besides our in-house developed IoT sensors, the AMBIsense data framework perfectly allows you to integrate your own or 3rd party measurement devices.
Our various sound sensing solutions enable environmental sound monitoring and proactive situational management strategies, allowing administrators to swiftly respond to noise disturbances, illegal activities, and security threats. By harnessing advanced technology, AMBIsense empowers stakeholders to create safer, healthier, and higher quality living environments for their communities.
Our sensor nodes analyze sound in a way that is highly similar to how humans listen to sound. Through the use of artificial neural networks and state-of-the-art machine learning methods, they can detect and classify sounds according to their source, and in this way provide an idea of how the acoustic environment would be perceived. This can be used to evaluate existing soundscapes, but our algorithms can also be applied to simulated or auralized environments, such that soundscape design measures can be evaluated.
Our sensor nodes can act cooperatively, creating multi-device arrays. Through a combination of multi-sensor time/direction-of-arrival and cross-correlation analyses, the location of sound sources (impulsive, intermittent or stationary) can be estimated. We have a particular experience with the localization of low-frequency sound sources, for which typically large arrays are needed.
An array of sensor nodes allows to map the soundscape of extensive areas with great spatial detail, particularly urban areas, squares and parks. As such a noise heat map can be derived out of the processed noise data. On the one hand this will identify ánd localize noise disturbances originating from various sources such as nightlife, construction sites, traffic, heavy vehicles, …but as well highlight quiet zones and quiet hours.
The fixed sensor setup can be extended with mobile sensors with GPS which are used to refine dynamic noise maps, through a model-based spatio-temporal interpolation technique.
A noise heat map objectifies sound disturbances and presents them in a clear, readable overview. This is an essential dimension in the Digital Twin of any urban area.
Monitoring environmental noise also enables the correlation of data with the Sleep Disturbance Index and WHO noise level regulations, providing insights into which urban areas face public health challenges due to noise. Health sound monitoring will become an integral component of the smart cities of tomorrow.
Our sensing solutions provide all common noise metrics (LAeq, Lden, percentile levels etc.) on-the-fly at custom intervals, and allow to assess a wide range of advanced sound indicators, including psycho-acoustical indicators (loudness, sharpness, roughness, tonality) or state-of-the-art sound metrics such as the Common Noise Index, with an arbitrary temporal resolution. On top of that we have 1/3-octave band spectrum with a temporal resolution of 1/8s. We can even add your own designed indicator!
Direct noise management facilitates the immediate identification and mitigation of noise disturbances and nuisances in areas typically affected by nightlife activities, thereby enhancing the area’s sustainability. When sensor nodes detect specific disturbances such as noisy gatherings, shouting, singing, or loud music from boomboxes in public spaces, a (friendly) message can be projected onto the ground or displayed on an outdoor LED screen. This gentle approach encourages individuals to lower their voices or modify their activities.
Additionally, our AMBIsense solutions can detect anti-social behaviors such as driving so-called ‘boomcars’ with excessively loud music or scooters equipped with thundering aftermarket exhausts. Precise identification, including source localization and tracking, can be swiftly forwarded to police dispatch for appropriate action.
Further examples include the reporting of noisy quads or dirt bikes traversing outdoor nature trails.
Sensing the environment intelligently provides accurate situational awareness, akin to human perception. This enables public lighting systems to respond appropriately to real-time conditions. For example, lights can remain illuminated beyond regular hours to accommodate bustling restaurant terraces on a warm summer night, or dim when outdoor areas are vacant during rainy evenings.
Moreover, specific events such as a pedestrian passing by in the dark or, in more critical instances, a panic detection, can trigger the lights to increase brightness, enhancing safety in the surrounding environment.
Our technology is designed to detect, classify, localize, and alert to various events within the sensor node field’s action radius. It can identify specific events such as gunshots and explosions, as well as other occurrences including car and fire alarms, accidents, and situations indicating aggression or panic. This is achieved through continuous and comprehensive spectro-temporal analysis of sound and vibration. This makes our smart sound monitoring technology well suited for security applications.
A specific noise nuisance example our AMBIsense solution adeptly monitors is the detection and identification of ‘Boomcar’ nuisances, offering precise source localization and tracking of these disruptive vehicles with pumped-up engine noises and music-blasters.
Similarly, we effectively monitor and track the unauthorized presence of quads and dirt bikes in rural area’s, nature parks and nature trails intended for hikers and bicycles, ensuring the preservation of these serene environments.
Smart sensing technology enables the recognition and classification of specific environmental sounds. An AMBIsense sensor setup can not only detect traffic near the sensor node but also identify and track the direction of the sound. This capability allows counting of passing bicycles, motorcycles, cars, trucks and buses. Even the sound of pedestrians walking by can be detected.
Sound detection provides a non-intrusive, cost-effective solution compared to traditional camera surveillance. Equipped with multi-classification smart sensing technology and event detection capabilities, it can be deployed in various settings, including public spaces, private properties and industrial sites.
One notable application is drone detection in high-security areas such as airports, harbors, bank offices, prison facilities, warehouses, and industrial sites.
The smart sensor nodes can be modeled to capture and distinguish nature sounds, encompassing wildlife activity within natural habitats. This capability facilitates targeted wildlife search and tracking while simultaneously monitoring the entirety of the natural soundscape.
Sound contains a wealth of information. We provide solutions to derive information on the local state of the environment on the basis of the analysis of sound/vibration combined with machine learning. Some examples are monitoring the proper functioning of machines based on the noise they generate, or the detection of pavement wear on the basis of tire-road noise (for the latter, see our PAVEsense service).
Noise, mostly of low-frequency nature, generated by sources within this area, is often a cause of annoyance for residents of the nearby city of Oostvoorne, located 3km to the south of the area. In order not to impede potential future expansion of the Rotterdam harbour, it is important that the sources and mechanisms of this problem are known.
